Search

Your search keyword '"Wang, Qiuyue"' showing total 787 results
Start Over Author "Wang, Qiuyue"
787 results on '"Wang, Qiuyue"'

1. DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion

Author

He, Huiguo, Yang, Huan, Tuo, Zixi, Zhou, Yuan, Wang, Qiuyue, Zhang, Yuhang, Liu, Zeyu, Huang, Wenhao, Chao, Hongyang, and Yin, Jian

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Multimedia
Abstract

Story visualization aims to create visually compelling images or videos corresponding to textual narratives. Despite recent advances in diffusion models yielding promising results, existing methods still struggle to create a coherent sequence of subject-consistent frames based solely on a story. To this end, we propose DreamStory, an automatic open-domain story visualization framework by leveraging the LLMs and a novel multi-subject consistent diffusion model. DreamStory consists of (1) an LLM acting as a story director and (2) an innovative Multi-Subject consistent Diffusion model (MSD) for generating consistent multi-subject across the images. First, DreamStory employs the LLM to generate descriptive prompts for subjects and scenes aligned with the story, annotating each scene's subjects for subsequent subject-consistent generation. Second, DreamStory utilizes these detailed subject descriptions to create portraits of the subjects, with these portraits and their corresponding textual information serving as multimodal anchors (guidance). Finally, the MSD uses these multimodal anchors to generate story scenes with consistent multi-subject. Specifically, the MSD includes Masked Mutual Self-Attention (MMSA) and Masked Mutual Cross-Attention (MMCA) modules. MMSA and MMCA modules ensure appearance and semantic consistency with reference images and text, respectively. Both modules employ masking mechanisms to prevent subject blending. To validate our approach and promote progress in story visualization, we established a benchmark, DS-500, which can assess the overall performance of the story visualization framework, subject-identification accuracy, and the consistency of the generation model. Extensive experiments validate the effectiveness of DreamStory in both subjective and objective evaluations. Please visit our project homepage at https://dream-xyz.github.io/dreamstory.

Published
2024

4. VLM-Eval: A General Evaluation on Video Large Language Models

Author

Li, Shuailin, Zhang, Yuang, Zhao, Yucheng, Wang, Qiuyue, Jia, Fan, Liu, Yingfei, and Wang, Tiancai

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Despite the rapid development of video Large Language Models (LLMs), a comprehensive evaluation is still absent. In this paper, we introduce a unified evaluation that encompasses multiple video tasks, including captioning, question and answering, retrieval, and action recognition. In addition to conventional metrics, we showcase how GPT-based evaluation can match human-like performance in assessing response quality across multiple aspects. We propose a simple baseline: Video-LLaVA, which uses a single linear projection and outperforms existing video LLMs. Finally, we evaluate video LLMs beyond academic datasets, which show encouraging recognition and reasoning capabilities in driving scenarios with only hundreds of video-instruction pairs for fine-tuning. We hope our work can serve as a unified evaluation for video LLMs, and help expand more practical scenarios. The evaluation code will be available soon.

Published
2023

5. A High-Dimensional Data Trust Publishing Method Based on Attention Mechanism and Differential Privacy

Author

Li, Taiqiang, Zhang, Zhen, Qian, Heng, Wang, Qiuyue, Su, Guanqun, Meng, Lingzhen, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Huang, De-Shuang, editor, Chen, Wei, editor, and Guo, Jiayang, editor

Published
2024
Full Text
View/download PDF

13. EROSION RESISTANCE OF PRE-TREATED RICE HUSK ASH CONCRETE UNDER SIMULATED ACID RAIN

Author

Pengfei Qiu, Ercong Meng, Wang Qiuyue, and Wu Dake

Subjects
pre-treatment, rice husk ash, concrete, dry-wet cycle, acid rain, compound acid solution, Clay industries. Ceramics. Glass, TP785-869
Abstract

In order to explore the ability of pre-treated rice husk ash concrete to resist acid rain erosion, this study investigates the deterioration law of ordinary concrete and pre-treated rice husk ash concrete under the combined action of acid rain erosion and dry-wet cycles, combining microscopic changes and a series of indicators such as the compressive strength of the concrete, with the dry-wet cycle of clean water as a control to analyse the deterioration law of the concrete. The results show that when the replacement rate of the pre-treated rice husk ash is 10%, the compressive strength of the concrete is the most improved and the splitting tensile strength is negatively correlated with the substitution rate of P-RHA. From the durability of the concrete, with the progress of the dry-wet cycle, the mass, compressive strength, and relative dynamic elasticity modulus show a decreasing trend, and the water absorption shows an upward trend. According to microscopic changes, the two types of concrete are mainly eroded by gypsum. The addition of P-RHA can promote the growth of C-S-H gels, reduce the effective porosity of the concrete, and delay the deterioration time of the concrete. By analysing the depth of the degradation of the concrete′s compressive strength, it is concluded that the ordinary concrete is destroyed earlier than the P-RHA concrete.

Published
2023
Full Text
View/download PDF

22. Confidence-aware Adversarial Learning for Self-supervised Semantic Matching

Author

Huang, Shuaiyi, Wang, Qiuyue, and He, Xuming

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

In this paper, we aim to address the challenging task of semantic matching where matching ambiguity is difficult to resolve even with learned deep features. We tackle this problem by taking into account the confidence in predictions and develop a novel refinement strategy to correct partial matching errors. Specifically, we introduce a Confidence-Aware Semantic Matching Network (CAMNet) which instantiates two key ideas of our approach. First, we propose to estimate a dense confidence map for a matching prediction through self-supervised learning. Second, based on the estimated confidence, we refine initial predictions by propagating reliable matching to the rest of locations on the image plane. In addition, we develop a new hybrid loss in which we integrate a semantic alignment loss with a confidence loss, and an adversarial loss that measures the quality of semantic correspondence. We are the first that exploit confidence during refinement to improve semantic matching accuracy and develop an end-to-end self-supervised adversarial learning procedure for the entire matching network. We evaluate our method on two public benchmarks, on which we achieve top performance over the prior state of the art. We will release our source code at https://github.com/ShuaiyiHuang/CAMNet., Comment: PRCV 2020

Published
2020

23. Dynamic Context Correspondence Network for Semantic Alignment

Author

Huang, Shuaiyi, Wang, Qiuyue, Zhang, Songyang, Yan, Shipeng, and He, Xuming

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Establishing semantic correspondence is a core problem in computer vision and remains challenging due to large intra-class variations and lack of annotated data. In this paper, we aim to incorporate global semantic context in a flexible manner to overcome the limitations of prior work that relies on local semantic representations. To this end, we first propose a context-aware semantic representation that incorporates spatial layout for robust matching against local ambiguities. We then develop a novel dynamic fusion strategy based on attention mechanism to weave the advantages of both local and context features by integrating semantic cues from multiple scales. We instantiate our strategy by designing an end-to-end learnable deep network, named as Dynamic Context Correspondence Network (DCCNet). To train the network, we adopt a multi-auxiliary task loss to improve the efficiency of our weakly-supervised learning procedure. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including PF-Pascal, PF-Willow, and TSS, demonstrating its effectiveness and generality., Comment: ICCV 2019

Published
2019

31. A multicenter prospective study of comprehensive metagenomic and transcriptomic signatures for predicting outcomes of patients with severe community-acquired pneumonia

Author

Zhao, Jingya, He, Xiangyan, Min, Jiumeng, Yao, Rosary Sin Yu, Chen, Yu, Chen, Zhonglin, Huang, Yi, Zhu, Zhongyi, Gong, Yanping, Xie, Yusang, Li, Yuping, Luo, Weiwei, Shi, Dongwei, Xu, Jinfu, Shen, Ao, Wang, Qiuyue, Sun, Ruixue, He, Bei, Lin, Yang, Shen, Ning, Cao, Bin, Yang, Lingling, She, Danyang, Shi, Yi, Zhou, Jiali, Su, Xin, Zhou, Hua, Ma, Zhenzi, Fan, Hong, Lin, Yongquan, Ye, Feng, Nie, Xifang, Zhang, Qiao, Tian, Xinlun, Lai, Guoxiang, Zhou, Min, Ma, Jinmin, Zhang, Jing, and Qu, Jieming

Published
2023
Full Text
View/download PDF

48. Associations of residential greenness with lung function and chronic obstructive pulmonary disease in China

Author

Xiao, Yalan, Gu, Xiaoying, Niu, Hongtao, Meng, Xia, Zhang, Lina, Xu, Jianying, Yang, Lan, Zhao, Jianping, Zhang, Xiangyan, Bai, Chunxue, Kang, Jian, Ran, Pixin, Shen, Huahao, Wen, Fuqiang, Huang, Kewu, Chen, Yahong, Sun, Tieying, Shan, Guangliang, Lin, Yingxiang, Wu, Sinan, Zhu, Jianguo, Wang, Ruiying, Shi, Zhihong, Xu, Yongjian, Ye, Xianwei, Song, Yuanlin, Wang, Qiuyue, Zhou, Yumin, Ding, Liren, Li, Diandian, Yao, Wanzhen, Guo, Yanfei, Xiao, Fei, Lu, Yong, Peng, Xiaoxia, Zhang, Biao, Xiao, Dan, Wang, Zuomin, Zhang, Hong, Bu, Xiaoning, Zhang, Xiaolei, An, Li, Zhang, Shu, Cao, Zhixin, Zhan, Qingyuan, Yang, Yuanhua, Liang, Lirong, Cao, Bin, Dai, Huaping, Wu, Tangchun, He, Jiang, Kan, Haidong, Chen, Renjie, Yang, Ting, and Wang, Chen

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results